Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     achievement
    -0.07
     caliente
    -0.07
    nf
    -0.07
     Flip
    -0.07
    Laughs
    -0.07
     관계
    -0.06
    ejs
    -0.06
    ække
    -0.06
    .ro
    -0.06
     Duch
    -0.06
    POSITIVE LOGITS
    ạt
    0.07
     blob
    0.07
    アル
    0.07
    (mean
    0.07
    吐
    0.06
    ffects
    0.06
     vir
    0.06
    incoming
    0.06
     Vul
    0.06
       
    0.06
    Act Density 0.008%

    No Known Activations